© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3349
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being unaltered or unchanged over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of things remaining constant or unchanged

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aph
    -0.69
     Typhoon
    -0.68
    ingo
    -0.68
    RA
    -0.65
    GPU
    -0.65
    eur
    -0.63
    alez
    -0.63
    AMS
    -0.62
     Bees
    -0.62
    RH
    -0.61
    POSITIVE LOGITS
     unchanged
    1.30
    theless
    0.98
     untouched
    0.91
     unaffected
    0.88
     unbeaten
    0.76
    withstanding
    0.76
    inant
    0.74
    aneously
    0.72
    iated
    0.69
    ilibrium
    0.69
    Activations Density 0.008%

    No Known Activations